{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.40574049949646, "min": 1.40574049949646, "max": 1.427527904510498, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70888.6796875, "min": 68943.5625, "max": 77334.1875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.4130081300813, "min": 78.85805422647528, "max": 401.1111111111111, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49454.0, "min": 48900.0, "max": 50540.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999330.0, "min": 49976.0, "max": 1999330.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999330.0, "min": 49976.0, "max": 1999330.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4627349376678467, "min": 0.1452723741531372, "max": 2.4759154319763184, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1514.58203125, "min": 18.159046173095703, "max": 1514.58203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8435040901346906, "min": 1.8287471690177917, "max": 3.951711715967863, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2363.7550154328346, "min": 228.59339612722397, "max": 2393.1759556531906, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8435040901346906, "min": 1.8287471690177917, "max": 3.951711715967863, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2363.7550154328346, "min": 228.59339612722397, "max": 2393.1759556531906, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015730512515134857, "min": 0.014228598209350216, "max": 0.02160498290937135, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.031461025030269714, "min": 0.028457196418700433, "max": 0.06481494872811405, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.059050972759723666, "min": 0.020718547670791548, "max": 0.06745942942798139, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.11810194551944733, "min": 0.041437095341583095, "max": 0.18879190596441428, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.6900734366749955e-06, "min": 4.6900734366749955e-06, "max": 0.00029527500157499996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.380146873349991e-06, "min": 9.380146873349991e-06, "max": 0.00084381736872755, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10156332499999998, "min": 0.10156332499999998, "max": 0.198425, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20312664999999996, "min": 0.20312664999999996, "max": 0.58127245, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.800991749999997e-05, "min": 8.800991749999997e-05, "max": 0.0049214075, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017601983499999994, "min": 0.00017601983499999994, "max": 0.014065495255000001, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1738661160", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738663556" }, "total": 2395.923138584, "count": 1, "self": 0.436843191999742, "children": { "run_training.setup": { "total": 0.023745201000110683, "count": 1, "self": 0.023745201000110683 }, "TrainerController.start_learning": { "total": 2395.462550191, "count": 1, "self": 4.476073271941004, "children": { "TrainerController._reset_env": { "total": 3.0938779059997614, "count": 1, "self": 3.0938779059997614 }, "TrainerController.advance": { "total": 2387.7727500990595, "count": 232553, "self": 4.4741919177395175, "children": { "env_step": { "total": 1895.8848548591, "count": 232553, "self": 1481.6656496720652, "children": { "SubprocessEnvManager._take_step": { "total": 411.6366704329321, "count": 232553, "self": 15.323441919805646, "children": { "TorchPolicy.evaluate": { "total": 396.31322851312643, "count": 222898, "self": 396.31322851312643 } } }, "workers": { "total": 2.582534754102653, "count": 232553, "self": 0.0, "children": { "worker_root": { "total": 2388.180904726953, "count": 232553, "is_parallel": true, "self": 1178.2073680848243, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010102209998876788, "count": 1, "is_parallel": true, "self": 0.000265441000010469, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007447799998772098, "count": 2, "is_parallel": true, "self": 0.0007447799998772098 } } }, "UnityEnvironment.step": { "total": 0.029026623999925505, "count": 1, "is_parallel": true, "self": 0.0002649449997988995, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018386700003247824, "count": 1, "is_parallel": true, "self": 0.00018386700003247824 }, "communicator.exchange": { "total": 0.027763432000028843, "count": 1, "is_parallel": true, "self": 0.027763432000028843 }, "steps_from_proto": { "total": 0.0008143800000652845, "count": 1, "is_parallel": true, "self": 0.000183766000191099, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006306139998741855, "count": 2, "is_parallel": true, "self": 0.0006306139998741855 } } } } } } }, "UnityEnvironment.step": { "total": 1209.9735366421287, "count": 232552, "is_parallel": true, "self": 36.27187437963312, "children": { "UnityEnvironment._generate_step_input": { "total": 78.13466776593668, "count": 232552, "is_parallel": true, "self": 78.13466776593668 }, "communicator.exchange": { "total": 1011.266354671834, "count": 232552, "is_parallel": true, "self": 1011.266354671834 }, "steps_from_proto": { "total": 84.30063982472484, "count": 232552, "is_parallel": true, "self": 29.40275369184792, "children": { "_process_rank_one_or_two_observation": { "total": 54.89788613287692, "count": 465104, "is_parallel": true, "self": 54.89788613287692 } } } } } } } } } } }, "trainer_advance": { "total": 487.41370332222004, "count": 232553, "self": 6.369718724219638, "children": { "process_trajectory": { "total": 160.37858713199785, "count": 232553, "self": 158.95267364099936, "children": { "RLTrainer._checkpoint": { "total": 1.4259134909984823, "count": 10, "self": 1.4259134909984823 } } }, "_update_policy": { "total": 320.66539746600256, "count": 96, "self": 255.4020919519885, "children": { "TorchPPOOptimizer.update": { "total": 65.26330551401406, "count": 2880, "self": 65.26330551401406 } } } } } } }, "trainer_threads": { "total": 8.750002962187864e-07, "count": 1, "self": 8.750002962187864e-07 }, "TrainerController._save_models": { "total": 0.11984803899940744, "count": 1, "self": 0.0021602739998343168, "children": { "RLTrainer._checkpoint": { "total": 0.11768776499957312, "count": 1, "self": 0.11768776499957312 } } } } } } }